From patchwork Wed May 30 19:30:45 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Darrick J. Wong" X-Patchwork-Id: 10439669 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id A724B602BD for ; Wed, 30 May 2018 19:30:51 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 894A829177 for ; Wed, 30 May 2018 19:30:51 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 7D02F291C7; Wed, 30 May 2018 19:30:51 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.8 required=2.0 tests=BAYES_00,DKIM_SIGNED, MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI, T_DKIM_INVALID, UNPARSEABLE_RELAY autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 33CF429177 for ; Wed, 30 May 2018 19:30:50 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753627AbeE3Tat (ORCPT ); Wed, 30 May 2018 15:30:49 -0400 Received: from aserp2120.oracle.com ([141.146.126.78]:60372 "EHLO aserp2120.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753442AbeE3Tas (ORCPT ); Wed, 30 May 2018 15:30:48 -0400 Received: from pps.filterd (aserp2120.oracle.com [127.0.0.1]) by aserp2120.oracle.com (8.16.0.22/8.16.0.22) with SMTP id w4UJPijH063381 for ; Wed, 30 May 2018 19:30:48 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=oracle.com; h=subject : from : to : cc : date : message-id : in-reply-to : references : mime-version : content-type : content-transfer-encoding; s=corp-2017-10-26; bh=cYHncVkLAP/kWXKK7js7Muo324WOQacyfiRix3LYkHQ=; b=QvdAvSlsUDxovwbRNIKMrPSeqAS86RtEcNXmufX1pTyU1p8wufU3Q3FqUZKyHeUlTptp eLMLhUfecCP0VewhjnPRRXtkrpmJuP2B0chlzE4mTm4gK8RU90iqwn0SENuBSNnZ0qMi fz38nFlytYJYfiKoQ7jtsMOl7oLtivd+qWf/RsT+x/dCJ9a+TmTskQudIjXAz4gLATI1 zzIujzz/rArpCRodqbOz19vpTwfpcMPyDT+mZuuOndP5V0nGWiJqwl0pF45sYVu+JH0s 8bYYJvIzmgnyVhsz9ROvi6fkW5ZG+4/wuqCnqe1FeLCr+ae6FgVnD/EzA4wGxqaAAl2n yQ== Received: from aserv0021.oracle.com (aserv0021.oracle.com [141.146.126.233]) by aserp2120.oracle.com with ESMTP id 2j9ev8c0v3-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK) for ; Wed, 30 May 2018 19:30:47 +0000 Received: from aserv0122.oracle.com (aserv0122.oracle.com [141.146.126.236]) by aserv0021.oracle.com (8.14.4/8.14.4) with ESMTP id w4UJUl9J000462 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK) for ; Wed, 30 May 2018 19:30:47 GMT Received: from abhmp0005.oracle.com (abhmp0005.oracle.com [141.146.116.11]) by aserv0122.oracle.com (8.14.4/8.14.4) with ESMTP id w4UJUl24030870 for ; Wed, 30 May 2018 19:30:47 GMT Received: from localhost (/10.159.253.45) by default (Oracle Beehive Gateway v4.0) with ESMTP ; Wed, 30 May 2018 12:30:46 -0700 Subject: [PATCH 01/14] xfs: repair the AGF and AGFL From: "Darrick J. Wong" To: darrick.wong@oracle.com Cc: linux-xfs@vger.kernel.org Date: Wed, 30 May 2018 12:30:45 -0700 Message-ID: <152770864591.11611.5564813732568495676.stgit@magnolia> In-Reply-To: <152770863951.11611.5866814627357136911.stgit@magnolia> References: <152770863951.11611.5866814627357136911.stgit@magnolia> User-Agent: StGit/0.17.1-dirty MIME-Version: 1.0 X-Proofpoint-Virus-Version: vendor=nai engine=5900 definitions=8909 signatures=668702 X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 suspectscore=4 malwarescore=0 phishscore=0 bulkscore=0 spamscore=0 mlxscore=0 mlxlogscore=999 adultscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1805220000 definitions=main-1805300207 Sender: linux-xfs-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-xfs@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Darrick J. Wong Regenerate the AGF and AGFL from the rmap data. Signed-off-by: Darrick J. Wong --- fs/xfs/scrub/agheader_repair.c | 484 ++++++++++++++++++++++++++++++++++++++++ fs/xfs/scrub/repair.c | 30 ++ fs/xfs/scrub/repair.h | 6 fs/xfs/scrub/scrub.c | 4 fs/xfs/xfs_trans.c | 54 ++++ fs/xfs/xfs_trans.h | 2 6 files changed, 578 insertions(+), 2 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe linux-xfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 8b91e9ebe1e7..0f794d27382a 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -31,12 +31,18 @@ #include "xfs_sb.h" #include "xfs_inode.h" #include "xfs_alloc.h" +#include "xfs_alloc_btree.h" #include "xfs_ialloc.h" +#include "xfs_ialloc_btree.h" #include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_refcount.h" +#include "xfs_refcount_btree.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" +#include "scrub/repair.h" /* Superblock */ @@ -68,3 +74,481 @@ xfs_repair_superblock( xfs_trans_log_buf(sc->tp, bp, 0, BBTOB(bp->b_length) - 1); return error; } + +/* AGF */ + +struct xfs_repair_agf_allocbt { + struct xfs_scrub_context *sc; + xfs_agblock_t freeblks; + xfs_agblock_t longest; +}; + +/* Record free space shape information. */ +STATIC int +xfs_repair_agf_walk_allocbt( + struct xfs_btree_cur *cur, + struct xfs_alloc_rec_incore *rec, + void *priv) +{ + struct xfs_repair_agf_allocbt *raa = priv; + int error = 0; + + if (xfs_scrub_should_terminate(raa->sc, &error)) + return error; + + raa->freeblks += rec->ar_blockcount; + if (rec->ar_blockcount > raa->longest) + raa->longest = rec->ar_blockcount; + return error; +} + +/* Does this AGFL block look sane? */ +STATIC int +xfs_repair_agf_check_agfl_block( + struct xfs_mount *mp, + xfs_agblock_t agbno, + void *priv) +{ + struct xfs_scrub_context *sc = priv; + + if (!xfs_verify_agbno(mp, sc->sa.agno, agbno)) + return -EFSCORRUPTED; + return 0; +} + +/* Repair the AGF. */ +int +xfs_repair_agf( + struct xfs_scrub_context *sc) +{ + struct xfs_repair_find_ag_btree fab[] = { + { + .rmap_owner = XFS_RMAP_OWN_AG, + .buf_ops = &xfs_allocbt_buf_ops, + .magic = XFS_ABTB_CRC_MAGIC, + }, + { + .rmap_owner = XFS_RMAP_OWN_AG, + .buf_ops = &xfs_allocbt_buf_ops, + .magic = XFS_ABTC_CRC_MAGIC, + }, + { + .rmap_owner = XFS_RMAP_OWN_AG, + .buf_ops = &xfs_rmapbt_buf_ops, + .magic = XFS_RMAP_CRC_MAGIC, + }, + { + .rmap_owner = XFS_RMAP_OWN_REFC, + .buf_ops = &xfs_refcountbt_buf_ops, + .magic = XFS_REFC_CRC_MAGIC, + }, + { + .buf_ops = NULL, + }, + }; + struct xfs_repair_agf_allocbt raa; + struct xfs_agf old_agf; + struct xfs_mount *mp = sc->mp; + struct xfs_buf *agf_bp; + struct xfs_buf *agfl_bp; + struct xfs_agf *agf; + struct xfs_btree_cur *cur = NULL; + struct xfs_perag *pag; + xfs_agblock_t blocks; + xfs_agblock_t freesp_blocks; + int64_t delta_fdblocks = 0; + int error; + + /* We require the rmapbt to rebuild anything. */ + if (!xfs_sb_version_hasrmapbt(&mp->m_sb)) + return -EOPNOTSUPP; + + xfs_scrub_perag_get(sc->mp, &sc->sa); + pag = sc->sa.pag; + memset(&raa, 0, sizeof(raa)); + error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp, + XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGF_DADDR(mp)), + XFS_FSS_TO_BB(mp, 1), 0, &agf_bp, NULL); + if (error) + return error; + agf_bp->b_ops = &xfs_agf_buf_ops; + + /* + * Load the AGFL so that we can screen out OWN_AG blocks that + * are on the AGFL now; these blocks might have once been part + * of the bno/cnt/rmap btrees but are not now. + */ + error = xfs_alloc_read_agfl(mp, sc->tp, sc->sa.agno, &agfl_bp); + if (error) + return error; + error = xfs_agfl_walk(sc->mp, XFS_BUF_TO_AGF(agf_bp), agfl_bp, + xfs_repair_agf_check_agfl_block, sc); + if (error) + return error; + + /* Find the btree roots. */ + error = xfs_repair_find_ag_btree_roots(sc, agf_bp, fab, agfl_bp); + if (error) + return error; + if (fab[0].root == NULLAGBLOCK || fab[0].height > XFS_BTREE_MAXLEVELS || + fab[1].root == NULLAGBLOCK || fab[1].height > XFS_BTREE_MAXLEVELS || + fab[2].root == NULLAGBLOCK || fab[2].height > XFS_BTREE_MAXLEVELS) + return -EFSCORRUPTED; + if (xfs_sb_version_hasreflink(&mp->m_sb) && + (fab[3].root == NULLAGBLOCK || fab[3].height > XFS_BTREE_MAXLEVELS)) + return -EFSCORRUPTED; + + /* Start rewriting the header. */ + agf = XFS_BUF_TO_AGF(agf_bp); + memcpy(&old_agf, agf, sizeof(old_agf)); + + /* + * We relied on the rmapbt to reconstruct the AGF. If we get a + * different root then something's seriously wrong. + */ + if (be32_to_cpu(old_agf.agf_roots[XFS_BTNUM_RMAPi]) != fab[2].root) + return -EFSCORRUPTED; + memset(agf, 0, mp->m_sb.sb_sectsize); + agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC); + agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION); + agf->agf_seqno = cpu_to_be32(sc->sa.agno); + agf->agf_length = cpu_to_be32(xfs_ag_block_count(mp, sc->sa.agno)); + agf->agf_roots[XFS_BTNUM_BNOi] = cpu_to_be32(fab[0].root); + agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(fab[1].root); + agf->agf_roots[XFS_BTNUM_RMAPi] = cpu_to_be32(fab[2].root); + agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(fab[0].height); + agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(fab[1].height); + agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(fab[2].height); + agf->agf_flfirst = old_agf.agf_flfirst; + agf->agf_fllast = old_agf.agf_fllast; + agf->agf_flcount = old_agf.agf_flcount; + if (xfs_sb_version_hascrc(&mp->m_sb)) + uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid); + if (xfs_sb_version_hasreflink(&mp->m_sb)) { + agf->agf_refcount_root = cpu_to_be32(fab[3].root); + agf->agf_refcount_level = cpu_to_be32(fab[3].height); + } + + /* Update the AGF counters from the bnobt. */ + cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno, + XFS_BTNUM_BNO); + raa.sc = sc; + error = xfs_alloc_query_all(cur, xfs_repair_agf_walk_allocbt, &raa); + if (error) + goto err; + error = xfs_btree_count_blocks(cur, &blocks); + if (error) + goto err; + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + freesp_blocks = blocks - 1; + agf->agf_freeblks = cpu_to_be32(raa.freeblks); + agf->agf_longest = cpu_to_be32(raa.longest); + + /* Update the AGF counters from the cntbt. */ + cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno, + XFS_BTNUM_CNT); + error = xfs_btree_count_blocks(cur, &blocks); + if (error) + goto err; + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + freesp_blocks += blocks - 1; + + /* Update the AGF counters from the rmapbt. */ + cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno); + error = xfs_btree_count_blocks(cur, &blocks); + if (error) + goto err; + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + agf->agf_rmap_blocks = cpu_to_be32(blocks); + freesp_blocks += blocks - 1; + + /* Update the AGF counters from the refcountbt. */ + if (xfs_sb_version_hasreflink(&mp->m_sb)) { + cur = xfs_refcountbt_init_cursor(mp, sc->tp, agf_bp, + sc->sa.agno, NULL); + error = xfs_btree_count_blocks(cur, &blocks); + if (error) + goto err; + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + agf->agf_refcount_blocks = cpu_to_be32(blocks); + } + agf->agf_btreeblks = cpu_to_be32(freesp_blocks); + cur = NULL; + + /* Trigger reinitialization of the in-core data. */ + if (raa.freeblks != be32_to_cpu(old_agf.agf_freeblks)) { + delta_fdblocks += (int64_t)raa.freeblks - + be32_to_cpu(old_agf.agf_freeblks); + if (pag->pagf_init) + pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks); + } + + if (freesp_blocks != be32_to_cpu(old_agf.agf_btreeblks)) { + delta_fdblocks += (int64_t)freesp_blocks - + be32_to_cpu(old_agf.agf_btreeblks); + if (pag->pagf_init) + pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks); + } + + if (pag->pagf_init && + (raa.longest != be32_to_cpu(old_agf.agf_longest) || + fab[0].height != be32_to_cpu(old_agf.agf_levels[XFS_BTNUM_BNOi]) || + fab[1].height != be32_to_cpu(old_agf.agf_levels[XFS_BTNUM_CNTi]) || + fab[2].height != be32_to_cpu(old_agf.agf_levels[XFS_BTNUM_RMAPi]) || + fab[3].height != be32_to_cpu(old_agf.agf_refcount_level))) { + pag->pagf_longest = be32_to_cpu(agf->agf_longest); + pag->pagf_levels[XFS_BTNUM_BNOi] = + be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNOi]); + pag->pagf_levels[XFS_BTNUM_CNTi] = + be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]); + pag->pagf_levels[XFS_BTNUM_RMAPi] = + be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]); + pag->pagf_refcount_level = + be32_to_cpu(agf->agf_refcount_level); + } + + error = xfs_repair_mod_fdblocks(sc, delta_fdblocks); + if (error) + goto err; + + /* Write this to disk. */ + xfs_trans_buf_set_type(sc->tp, agf_bp, XFS_BLFT_AGF_BUF); + xfs_trans_log_buf(sc->tp, agf_bp, 0, BBTOB(agf_bp->b_length) - 1); + return error; + +err: + if (cur) + xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : + XFS_BTREE_NOERROR); + memcpy(agf, &old_agf, sizeof(old_agf)); + return error; +} + +/* AGFL */ + +struct xfs_repair_agfl { + struct xfs_repair_extent_list freesp_list; + struct xfs_repair_extent_list agmeta_list; + struct xfs_scrub_context *sc; +}; + +/* Record all freespace information. */ +STATIC int +xfs_repair_agfl_rmap_fn( + struct xfs_btree_cur *cur, + struct xfs_rmap_irec *rec, + void *priv) +{ + struct xfs_repair_agfl *ra = priv; + struct xfs_buf *bp; + xfs_fsblock_t fsb; + int i; + int error = 0; + + if (xfs_scrub_should_terminate(ra->sc, &error)) + return error; + + /* Record all the OWN_AG blocks... */ + if (rec->rm_owner == XFS_RMAP_OWN_AG) { + fsb = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_private.a.agno, + rec->rm_startblock); + error = xfs_repair_collect_btree_extent(ra->sc, + &ra->freesp_list, fsb, rec->rm_blockcount); + if (error) + return error; + } + + /* ...and all the rmapbt blocks... */ + for (i = 0; i < cur->bc_nlevels && cur->bc_ptrs[i] == 1; i++) { + xfs_btree_get_block(cur, i, &bp); + if (!bp) + continue; + fsb = XFS_DADDR_TO_FSB(cur->bc_mp, bp->b_bn); + error = xfs_repair_collect_btree_extent(ra->sc, + &ra->agmeta_list, fsb, 1); + if (error) + return error; + } + + return 0; +} + +/* Add a btree block to the agmeta list. */ +STATIC int +xfs_repair_agfl_visit_btblock( + struct xfs_btree_cur *cur, + int level, + void *priv) +{ + struct xfs_repair_agfl *ra = priv; + struct xfs_buf *bp; + xfs_fsblock_t fsb; + int error = 0; + + if (xfs_scrub_should_terminate(ra->sc, &error)) + return error; + + xfs_btree_get_block(cur, level, &bp); + if (!bp) + return 0; + + fsb = XFS_DADDR_TO_FSB(cur->bc_mp, bp->b_bn); + return xfs_repair_collect_btree_extent(ra->sc, &ra->agmeta_list, + fsb, 1); +} + +/* Repair the AGFL. */ +int +xfs_repair_agfl( + struct xfs_scrub_context *sc) +{ + struct xfs_repair_agfl ra; + struct xfs_owner_info oinfo; + struct xfs_mount *mp = sc->mp; + struct xfs_buf *agf_bp; + struct xfs_buf *agfl_bp; + struct xfs_agf *agf; + struct xfs_agfl *agfl; + struct xfs_btree_cur *cur = NULL; + __be32 *agfl_bno; + struct xfs_repair_extent *rae; + struct xfs_repair_extent *n; + xfs_agblock_t flcount; + xfs_agblock_t agbno; + xfs_agblock_t bno; + xfs_agblock_t old_flcount; + int error; + + /* We require the rmapbt to rebuild anything. */ + if (!xfs_sb_version_hasrmapbt(&mp->m_sb)) + return -EOPNOTSUPP; + + xfs_scrub_perag_get(sc->mp, &sc->sa); + xfs_repair_init_extent_list(&ra.freesp_list); + xfs_repair_init_extent_list(&ra.agmeta_list); + ra.sc = sc; + + error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.agno, 0, &agf_bp); + if (error) + return error; + if (!agf_bp) + return -ENOMEM; + + error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp, + XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGFL_DADDR(mp)), + XFS_FSS_TO_BB(mp, 1), 0, &agfl_bp, NULL); + if (error) + return error; + agfl_bp->b_ops = &xfs_agfl_buf_ops; + + /* Find all space used by the free space btrees & rmapbt. */ + cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno); + error = xfs_rmap_query_all(cur, xfs_repair_agfl_rmap_fn, &ra); + if (error) + goto err; + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + + /* Find all space used by bnobt. */ + cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno, + XFS_BTNUM_BNO); + error = xfs_btree_visit_blocks(cur, xfs_repair_agfl_visit_btblock, + &ra); + if (error) + goto err; + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + + /* Find all space used by cntbt. */ + cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno, + XFS_BTNUM_CNT); + error = xfs_btree_visit_blocks(cur, xfs_repair_agfl_visit_btblock, + &ra); + if (error) + goto err; + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + cur = NULL; + + /* + * Drop the freesp meta blocks that are in use by btrees. + * The remaining blocks /should/ be AGFL blocks. + */ + error = xfs_repair_subtract_extents(sc, &ra.freesp_list, + &ra.agmeta_list); + if (error) + goto err; + xfs_repair_cancel_btree_extents(sc, &ra.agmeta_list); + + /* Calculate the new AGFL size. */ + flcount = 0; + for_each_xfs_repair_extent_safe(rae, n, &ra.freesp_list) { + for (bno = 0; bno < rae->len; bno++) { + if (flcount >= xfs_agfl_size(mp) - 1) + break; + flcount++; + } + } + + /* Update fdblocks if flcount changed. */ + agf = XFS_BUF_TO_AGF(agf_bp); + old_flcount = be32_to_cpu(agf->agf_flcount); + if (flcount != old_flcount) { + int64_t delta_fdblocks = (int64_t)flcount - old_flcount; + + error = xfs_repair_mod_fdblocks(sc, delta_fdblocks); + if (error) + goto err; + if (sc->sa.pag->pagf_init) + sc->sa.pag->pagf_flcount = flcount; + } + + /* Update the AGF pointers. */ + agf->agf_flfirst = cpu_to_be32(1); + agf->agf_flcount = cpu_to_be32(flcount); + agf->agf_fllast = cpu_to_be32(flcount); + + /* Start rewriting the header. */ + agfl = XFS_BUF_TO_AGFL(agfl_bp); + memset(agfl, 0xFF, mp->m_sb.sb_sectsize); + agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC); + agfl->agfl_seqno = cpu_to_be32(sc->sa.agno); + uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid); + + /* Fill the AGFL with the remaining blocks. */ + flcount = 0; + agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, agfl_bp); + for_each_xfs_repair_extent_safe(rae, n, &ra.freesp_list) { + agbno = XFS_FSB_TO_AGBNO(mp, rae->fsbno); + + trace_xfs_repair_agfl_insert(mp, sc->sa.agno, agbno, rae->len); + + for (bno = 0; bno < rae->len; bno++) { + if (flcount >= xfs_agfl_size(mp) - 1) + break; + agfl_bno[flcount + 1] = cpu_to_be32(agbno + bno); + flcount++; + } + rae->fsbno += bno; + rae->len -= bno; + if (rae->len) + break; + list_del(&rae->list); + kmem_free(rae); + } + + /* Write AGF and AGFL to disk. */ + xfs_alloc_log_agf(sc->tp, agf_bp, + XFS_AGF_FLFIRST | XFS_AGF_FLLAST | XFS_AGF_FLCOUNT); + xfs_trans_buf_set_type(sc->tp, agfl_bp, XFS_BLFT_AGFL_BUF); + xfs_trans_log_buf(sc->tp, agfl_bp, 0, BBTOB(agfl_bp->b_length) - 1); + + /* Dump any AGFL overflow. */ + xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG); + return xfs_repair_reap_btree_extents(sc, &ra.freesp_list, &oinfo, + XFS_AG_RESV_AGFL); +err: + xfs_repair_cancel_btree_extents(sc, &ra.agmeta_list); + xfs_repair_cancel_btree_extents(sc, &ra.freesp_list); + if (cur) + xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : + XFS_BTREE_NOERROR); + return error; +} diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index e3e8fba1c99c..5f31dc8af505 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -1087,3 +1087,33 @@ xfs_repair_ino_dqattach( return error; } + +/* + * We changed this AGF's free block count, so now we need to reset the global + * counters. We use the transaction to update the global counters, so if the + * AG free counts were low we have to ask the transaction for more block + * reservation before decreasing fdblocks. + * + * XXX: We ought to have some mechanism for checking and fixing the superblock + * counters (particularly if we're close to ENOSPC) but that's left as an open + * research question for now. + */ +int +xfs_repair_mod_fdblocks( + struct xfs_scrub_context *sc, + int64_t delta_fdblocks) +{ + int error; + + if (delta_fdblocks == 0) + return 0; + + if (delta_fdblocks < 0) { + error = xfs_trans_reserve_more(sc->tp, -delta_fdblocks, 0); + if (error) + return error; + } + + xfs_trans_mod_sb(sc->tp, XFS_TRANS_SB_FDBLOCKS, delta_fdblocks); + return 0; +} diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h index f2b0895294db..97794c281a23 100644 --- a/fs/xfs/scrub/repair.h +++ b/fs/xfs/scrub/repair.h @@ -98,11 +98,15 @@ int xfs_repair_find_ag_btree_roots(struct xfs_scrub_context *sc, struct xfs_buf *agfl_bp); void xfs_repair_force_quotacheck(struct xfs_scrub_context *sc, uint dqtype); int xfs_repair_ino_dqattach(struct xfs_scrub_context *sc); +int xfs_repair_mod_fdblocks(struct xfs_scrub_context *sc, + int64_t delta_fdblocks); /* Metadata repairers */ int xfs_repair_probe(struct xfs_scrub_context *sc); int xfs_repair_superblock(struct xfs_scrub_context *sc); +int xfs_repair_agf(struct xfs_scrub_context *sc); +int xfs_repair_agfl(struct xfs_scrub_context *sc); #else @@ -126,6 +130,8 @@ xfs_repair_calc_ag_resblks( #define xfs_repair_probe xfs_repair_notsupported #define xfs_repair_superblock xfs_repair_notsupported +#define xfs_repair_agf xfs_repair_notsupported +#define xfs_repair_agfl xfs_repair_notsupported #endif /* CONFIG_XFS_ONLINE_REPAIR */ diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 36db098ba583..0b523ab9b8b0 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -222,13 +222,13 @@ static const struct xfs_scrub_meta_ops meta_scrub_ops[] = { .type = ST_PERAG, .setup = xfs_scrub_setup_fs, .scrub = xfs_scrub_agf, - .repair = xfs_repair_notsupported, + .repair = xfs_repair_agf, }, [XFS_SCRUB_TYPE_AGFL]= { /* agfl */ .type = ST_PERAG, .setup = xfs_scrub_setup_fs, .scrub = xfs_scrub_agfl, - .repair = xfs_repair_notsupported, + .repair = xfs_repair_agfl, }, [XFS_SCRUB_TYPE_AGI] = { /* agi */ .type = ST_PERAG, diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index fc7ba75b8b69..5c24e66170fe 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -138,6 +138,60 @@ xfs_trans_dup( return ntp; } +/* + * Try to reserve more blocks for a transaction. The single use case we + * support is for online repair -- use a transaction to gather data without + * fear of btree cycle deadlocks; calculate how many blocks we really need + * from that data; and only then start modifying data. This can fail due to + * ENOSPC, so we have to be able to cancel the transaction. + */ +int +xfs_trans_reserve_more( + struct xfs_trans *tp, + uint blocks, + uint rtextents) +{ + struct xfs_mount *mp = tp->t_mountp; + bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0; + int error = 0; + + ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY)); + + /* + * Attempt to reserve the needed disk blocks by decrementing + * the number needed from the number available. This will + * fail if the count would go below zero. + */ + if (blocks > 0) { + error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd); + if (error != 0) + return -ENOSPC; + tp->t_blk_res += blocks; + } + + /* + * Attempt to reserve the needed realtime extents by decrementing + * the number needed from the number available. This will + * fail if the count would go below zero. + */ + if (rtextents > 0) { + error = xfs_mod_frextents(mp, -((int64_t)rtextents)); + if (error) { + error = -ENOSPC; + goto out_blocks; + } + tp->t_rtx_res += rtextents; + } + + return 0; +out_blocks: + if (blocks > 0) { + xfs_mod_fdblocks(mp, (int64_t)blocks, rsvd); + tp->t_blk_res -= blocks; + } + return error; +} + /* * This is called to reserve free disk blocks and log space for the * given transaction. This must be done before allocating any resources diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 29706b8b3bd4..7284555c4801 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -165,6 +165,8 @@ typedef struct xfs_trans { int xfs_trans_alloc(struct xfs_mount *mp, struct xfs_trans_res *resp, uint blocks, uint rtextents, uint flags, struct xfs_trans **tpp); +int xfs_trans_reserve_more(struct xfs_trans *tp, uint blocks, + uint rtextents); int xfs_trans_alloc_empty(struct xfs_mount *mp, struct xfs_trans **tpp); void xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t);